What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations

What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations. Bhattacharya, P., Ghosh, S., Zafar, M. B., Ghosh, S. K, & Ganguly, N. December 2022. ISBN: 2212.13897 Publication Title: arXiv [cs.IR]

Paper abstract bibtex 1 download

With over 500 million tweets posted per day, in Twitter, it is difficult for Twitter users to discover interesting content from the deluge of uninteresting posts. In this work, we present a novel, explainable, topical recommendation system, that utilizes social annotations, to help Twitter users discover tweets, on topics of their interest. A major challenge in using traditional rating dependent recommendation systems, like collaborative filtering and content based systems, in high volume social networks is that, due to attention scarcity most items do not get any ratings. Additionally, the fact that most Twitter users are passive consumers, with 44% users never tweeting, makes it very difficult to use user ratings for generating recommendations. Further, a key challenge in developing recommendation systems is that in many cases users reject relevant recommendations if they are totally unfamiliar with the recommended item. Providing a suitable explanation, for why the item is recommended, significantly improves the acceptability of recommendation. By virtue of being a topical recommendation system our method is able to present simple topical explanations for the generated recommendations. Comparisons with state-of-the-art matrix factorization based collaborative filtering, content based and social recommendations demonstrate the efficacy of the proposed approach.

@unpublished{bhattacharya_what_2022,
	title = {What {You} {Like}: {Generating} {Explainable} {Topical} {Recommendations} for {Twitter} {Using} {Social} {Annotations}},
	url = {http://arxiv.org/abs/2212.13897},
	abstract = {With over 500 million tweets posted per day, in Twitter, it is difficult
for Twitter users to discover interesting content from the deluge of
uninteresting posts. In this work, we present a novel, explainable,
topical recommendation system, that utilizes social annotations, to help
Twitter users discover tweets, on topics of their interest. A major
challenge in using traditional rating dependent recommendation systems,
like collaborative filtering and content based systems, in high volume
social networks is that, due to attention scarcity most items do not get
any ratings. Additionally, the fact that most Twitter users are passive
consumers, with 44\% users never tweeting, makes it very difficult to use
user ratings for generating recommendations. Further, a key challenge in
developing recommendation systems is that in many cases users reject
relevant recommendations if they are totally unfamiliar with the
recommended item. Providing a suitable explanation, for why the item is
recommended, significantly improves the acceptability of recommendation.
By virtue of being a topical recommendation system our method is able to
present simple topical explanations for the generated recommendations.
Comparisons with state-of-the-art matrix factorization based collaborative
filtering, content based and social recommendations demonstrate the
efficacy of the proposed approach.},
	author = {Bhattacharya, Parantapa and Ghosh, Saptarshi and Zafar, Muhammad Bilal and Ghosh, Soumya K and Ganguly, Niloy},
	month = dec,
	year = {2022},
	note = {ISBN: 2212.13897
Publication Title: arXiv [cs.IR]},
}

Downloads: 1

{"_id":"ohpiKXPZbmDsX5bRG","bibbaseid":"bhattacharya-ghosh-zafar-ghosh-ganguly-whatyoulikegeneratingexplainabletopicalrecommendationsfortwitterusingsocialannotations-2022","author_short":["Bhattacharya, P.","Ghosh, S.","Zafar, M. B.","Ghosh, S. K","Ganguly, N."],"bibdata":{"bibtype":"unpublished","type":"unpublished","title":"What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations","url":"http://arxiv.org/abs/2212.13897","abstract":"With over 500 million tweets posted per day, in Twitter, it is difficult for Twitter users to discover interesting content from the deluge of uninteresting posts. In this work, we present a novel, explainable, topical recommendation system, that utilizes social annotations, to help Twitter users discover tweets, on topics of their interest. A major challenge in using traditional rating dependent recommendation systems, like collaborative filtering and content based systems, in high volume social networks is that, due to attention scarcity most items do not get any ratings. Additionally, the fact that most Twitter users are passive consumers, with 44% users never tweeting, makes it very difficult to use user ratings for generating recommendations. Further, a key challenge in developing recommendation systems is that in many cases users reject relevant recommendations if they are totally unfamiliar with the recommended item. Providing a suitable explanation, for why the item is recommended, significantly improves the acceptability of recommendation. By virtue of being a topical recommendation system our method is able to present simple topical explanations for the generated recommendations. Comparisons with state-of-the-art matrix factorization based collaborative filtering, content based and social recommendations demonstrate the efficacy of the proposed approach.","author":[{"propositions":[],"lastnames":["Bhattacharya"],"firstnames":["Parantapa"],"suffixes":[]},{"propositions":[],"lastnames":["Ghosh"],"firstnames":["Saptarshi"],"suffixes":[]},{"propositions":[],"lastnames":["Zafar"],"firstnames":["Muhammad","Bilal"],"suffixes":[]},{"propositions":[],"lastnames":["Ghosh"],"firstnames":["Soumya","K"],"suffixes":[]},{"propositions":[],"lastnames":["Ganguly"],"firstnames":["Niloy"],"suffixes":[]}],"month":"December","year":"2022","note":"ISBN: 2212.13897 Publication Title: arXiv [cs.IR]","bibtex":"@unpublished{bhattacharya_what_2022,\n\ttitle = {What {You} {Like}: {Generating} {Explainable} {Topical} {Recommendations} for {Twitter} {Using} {Social} {Annotations}},\n\turl = {http://arxiv.org/abs/2212.13897},\n\tabstract = {With over 500 million tweets posted per day, in Twitter, it is difficult\nfor Twitter users to discover interesting content from the deluge of\nuninteresting posts. In this work, we present a novel, explainable,\ntopical recommendation system, that utilizes social annotations, to help\nTwitter users discover tweets, on topics of their interest. A major\nchallenge in using traditional rating dependent recommendation systems,\nlike collaborative filtering and content based systems, in high volume\nsocial networks is that, due to attention scarcity most items do not get\nany ratings. Additionally, the fact that most Twitter users are passive\nconsumers, with 44\\% users never tweeting, makes it very difficult to use\nuser ratings for generating recommendations. Further, a key challenge in\ndeveloping recommendation systems is that in many cases users reject\nrelevant recommendations if they are totally unfamiliar with the\nrecommended item. Providing a suitable explanation, for why the item is\nrecommended, significantly improves the acceptability of recommendation.\nBy virtue of being a topical recommendation system our method is able to\npresent simple topical explanations for the generated recommendations.\nComparisons with state-of-the-art matrix factorization based collaborative\nfiltering, content based and social recommendations demonstrate the\nefficacy of the proposed approach.},\n\tauthor = {Bhattacharya, Parantapa and Ghosh, Saptarshi and Zafar, Muhammad Bilal and Ghosh, Soumya K and Ganguly, Niloy},\n\tmonth = dec,\n\tyear = {2022},\n\tnote = {ISBN: 2212.13897\nPublication Title: arXiv [cs.IR]},\n}\n","author_short":["Bhattacharya, P.","Ghosh, S.","Zafar, M. B.","Ghosh, S. K","Ganguly, N."],"key":"bhattacharya_what_2022","id":"bhattacharya_what_2022","bibbaseid":"bhattacharya-ghosh-zafar-ghosh-ganguly-whatyoulikegeneratingexplainabletopicalrecommendationsfortwitterusingsocialannotations-2022","role":"author","urls":{"Paper":"http://arxiv.org/abs/2212.13897"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"unpublished","biburl":"https://api.zotero.org/users/6655/collections/3TB3KT36/items?key=VFvZhZXIoHNBbzoLZ1IM2zgf&format=bibtex&limit=100","dataSources":["HB6fr7bPytW2CAAzC","7KNAjxiv2tsagmbgY"],"keywords":[],"search_terms":["generating","explainable","topical","recommendations","twitter","using","social","annotations","bhattacharya","ghosh","zafar","ghosh","ganguly"],"title":"What You Like: Generating Explainable Topical Recommendations for Twitter Using Social Annotations","year":2022,"downloads":1}